Dynamic and targeted allocation of resources for coaching service

Abstract

A computer-implemented method for dynamically reallocating resources to users of a coaching service. The method can include initially allocating resources to users of the coaching service, receiving indications of activities of the users relative to their allocated resources, and comparing the activities relative to a reference value to produce an outcome including a likelihood that a target user will benefit from a target resource. Upon identifying the target user, a dynamic reallocation process deallocates the target resource from another user and reallocates the target resource to the target user.

The invention claimed is: 
     
       1. A computer-implemented method comprising:
 receiving, by a processor, over a communications network, a plurality of indications of activities of a plurality of users of a coaching service,
 wherein the activities relate to a plurality of resources allocated to the plurality of users, the plurality of resources including a plurality of time increments that provide access to a virtual coach of a coaching service and a plurality of physiological monitoring devices, 
 wherein the plurality of indications includes physiological parameter data generated by the plurality of physiological monitoring devices, and 
 wherein the plurality of resources is allocated to the plurality of users in accordance with respective coaching protocols associated with the virtual coach of the coaching service; 
 
 processing, by the processor, the plurality of indications of the activities with a dynamic resource allocation engine to:
 compare the plurality of indications of the activities to a threshold utilization value, and 
 determine, based on the comparison, a likelihood that a reallocation of a resource can increase utilization of the coaching service without inhibiting the coaching protocols of the plurality of users,
 wherein the dynamic resource allocation engine includes a machine learning algorithm that is trained based on an aggregate of indications of user activities and is configured to model when and what resource to allocate; and 
 
 
 based on an output of the dynamic resource allocation engine including the determined likelihood, effecting, by the processor, dynamic reallocation of assignments of the plurality of resources to scale the coaching service. 
 
     
     
       2. The method of  claim 1  further comprising, prior to receiving the plurality of indications of the activities:
 allocating the plurality of resources to the plurality of users including a first user and a second user,
 wherein the plurality of resources includes the plurality of time increments that authorize access to the virtual coach and the plurality of physiological monitoring devices, each configured to monitor a physiological parameter when worn by a respective user. 
 
 
     
     
       3. The method of  claim 2 , wherein a first resource includes a first time increment of the virtual coach that is allocated to the first user and a second resource includes a second time increment of the virtual coach that is allocated to the second user, the virtual coach being accessible by the plurality of users for a limited time period. 
     
     
       4. The method of  claim 3 , wherein a first activity indicates utilization of the coaching service during the first time increment by the first user and a second activity indicates utilization of the coaching service during the second time increment by the second user. 
     
     
       5. The method of  claim 4 , wherein the dynamic reallocation comprises:
 reallocating at least a portion of the first time increment from the first user to the second user when the utilization of the first time increment is less than the utilization of the second time increment. 
 
     
     
       6. The method of  claim 4 , wherein the first activity and the second activity include user inputs responsive to a reoccurring polling process of the plurality of users by the coaching service. 
     
     
       7. The method of  claim 3  further comprising, prior to effecting the dynamic reallocation:
 identifying a target user of the plurality of users; 
 deallocating assignment of the first resource from the first user or the second resource from the second user; and 
 allocating assignment of the deallocated first resource or the deallocated second resource to the target user. 
 
     
     
       8. The method of  claim 3 , wherein assignment of the first resource is dynamically reallocated to a target user of the plurality of users based on a physiological parameter of the target user monitored by a physiological monitoring device worn by the target user. 
     
     
       9. The method of  claim 2 , wherein effecting the dynamic reallocation comprises:
 ranking the plurality of resources based on a measure of availability or criticality; 
 prioritizing the plurality of users based on a measure of effective utilization of the plurality of resources; and 
 recommending a reallocation of the plurality of resources among the plurality of users based on the ranking of the plurality of resources and the prioritization of the plurality of users. 
 
     
     
       10. The method of  claim 2 , wherein effecting the dynamic reallocation comprises:
 separating the plurality of users into a plurality of groups, each group associated with a characteristic that is common to all users of the group; and 
 reallocating at least some of the plurality of resources on a per group basis. 
 
     
     
       11. The method of  claim 2 , wherein the first user is a diabetic user and a first coaching protocol includes a diabetes management program for the diabetic user. 
     
     
       12. The method of  claim 1 , wherein effecting the dynamic reallocation comprises:
 presenting an indication of a set of resources to the virtual coach, the set of resources being available for reallocation; and 
 receiving an indication that the virtual coach selected a resource from among the set of resources for a target user of the plurality of users. 
 
     
     
       13. A computer-implemented method comprising:
 allocating, by a processor, a pool of resources of a coaching service to a plurality of users that subscribe to the coaching service, the pool of resources including a virtual coach, a time increment of a virtual coach session, and a medical device; 
 processing, by the processor, indications of activities, associated with the allocated pool of resources, with a dynamic resource allocation engine to:
 compare the plurality of indications of the activities to a threshold utilization value, and 
 determine, based on the comparison, a likelihood that reallocation of at least one time increment can increase utilization of the coaching service without inhibiting coaching of the plurality of users,
 wherein the dynamic resource allocation engine includes a machine learning algorithm that is trained based on an aggregate of indications of activities and is configured to model when and what resource to allocate; 
 
 
 identifying by the processor, based on an output of the dynamic resource allocation engine, a target user of the plurality of users as having a historically higher utilization rate of at least some of the pool of resources compared to other users that have been allocated resources of the pool of resources; 
 upon identifying the target user, deallocating by the processor, assignment of a target resource from another user of the plurality of users; and 
 dynamically reallocating, by the processor, assignment of the deallocated target resource to the target user. 
 
     
     
       14. The method of  claim 13 , wherein the target user is identified based on an ongoing physiological measurement calculated by a sensor of a monitoring device worn by the target user. 
     
     
       15. The method of  claim 13 , wherein deallocating the target resource comprises:
 throttling a function or intensity of a medical service based on real-time or near real-time monitoring of a physiological parameter. 
 
     
     
       16. The method of  claim 13 , wherein the target user is identified based on at least one of standard clinical data, a prescription profile, a risk profile including a risk score based on amount or frequency of related events, or a self-identified measure of confidence to manage a disease. 
     
     
       17. The method of  claim 13 , wherein the target user is identified based on an activity profile of the user including a level of engagement with the coaching service over a selected time increment. 
     
     
       18. The method of  claim 13 , wherein the allocation is based on a unique factor of the target user, sensor data associated with the target user, an availability of a resource, or a global factor of the plurality of users. 
     
     
       19. A server computer comprising:
 one or more memories storing instructions of a coaching service that is configured to initiate a coaching session over a computer network for a virtual coach of a plurality of coaching recipients,
 wherein each coaching recipient is a user of a computer device capable of coupling to the server computer over the computer network; 
 
 one or more processors configured to execute the instructions stored on the one or more memories, causing each computing device to:
 allocate a plurality of time increments of the coaching service to the plurality of coaching recipients over the computer network; 
 process, by a dynamic resource allocation engine, indications of activities associated with the allocated plurality of time increments including causing the server computer to:
 compare the indications of the activities to a threshold utilization value, and 
 determine, based on the comparison, a likelihood that reallocation of at least one time increment can increase utilization of the coaching service without inhibiting coaching of a plurality of users,
 wherein the dynamic resource allocation engine includes a machine learning algorithm that is trained based on an aggregate of indications of activities and is configured to model when and what resource to allocate; 
 
 
 identify, based on an output of the dynamic resource allocation engine, a target coaching recipient of the plurality of coaching recipients as having a greater value of a metric relative to at least some of the plurality of coaching recipients; and 
 dynamically reallocate at least some of the plurality of time increments to the target coaching recipient from another coaching recipient with a lower value of the metric. 
 
 
     
     
       20. The server computer of  claim 19 , wherein the target coaching recipient is identified based on an activity profile of the coaching service. 
     
     
       21. The method of  claim 1 , wherein the machine learning algorithm includes a Naïve Bayes Classifier algorithm, a K Means Clustering algorithm, a Support Vector Machine algorithm, or an artificial neural network.